Overview

World models learn or encode how states, objects, and events evolve, often predicting what will happen under different actions or observations. These predictions can help agents plan ahead, learn with fewer real-world trials, test decisions safely, and reason about situations they cannot currently observe. Approaches range from latent-state predictors and action-conditioned video generators to object- or graph-based models, executable programs, and physics-informed dynamics. A central challenge is making predictions useful and reliable over long horizons: visual plausibility and one-step accuracy do not guarantee correct causal dynamics, persistent memory, or better decisions.

Latest papers

CardsList

402 papers38 papers in the last four weeks, down 51% on the four weeks before. 0.3% of all new papers.

  1. Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking

    Aug 7, 2026Devin Pereira, Willem ZuidemaLLM World ModelsLLM Planning

  2. TaskSense: Focusing on What Matters in World Models

    Aug 6, 2026SM Mazharul Islam, Manfred HuberWorld Model LearningWorld Models

  3. EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning

    Aug 6, 2026Zishan Xu, Zhiyuan Yao, Yuxin Chen +9LLM World ModelsAgentic RL

  4. From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models

    Aug 6, 2026Jiale Han, Xiang Li, Jing Qian +7World ModelsComputational Social Science

  5. DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model

    Aug 6, 2026Wenhao Lin, Chenyu Yu, Xingwei Lin +6LLM World ModelsLLM Guardrails

  6. Overcoming Statistical Bias in Action-Controllable World Models

    Aug 5, 2026Yuhong Shi, Zhenhao Chu, Jie Wei +3World ModelsAction-Conditioned World Models

  7. UniNav: A Unified World-Action Diffusion Model for Visual Navigation

    Aug 4, 2026Changqing Zhou, Yueru Luo, Zeyu Jiang +1Visual NavigationTrajectory Generation

  8. DreamQAS: Learning a Decision-Useful World Model for VQE-Efficient Quantum Architecture Search

    Jul 31, 2026Jiayang Niu, Yan Wang, Jie Li +4Quantum Architecture SearchWorld Models

  9. PhiZero: A World Model Built Around Physical Language

    Jul 30, 2026Shuyao Shang, Yuqi Wang, Ruopeng Gao +4Action-Conditioned Video GenerationPhysical Consistency in Video Generation

  10. Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3

    Jul 30, 2026Jens Lehmann, Andrei Aioanei, Sahar VahdatiGame-Playing AgentsAI Coding Agents

  11. ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow

    Jul 30, 2026Dongxiu Liu, Haoyi Niu, Peng Cheng +5Robotic ControlLatent Dynamics Modeling

  12. Failure Detection for Surgical Robot Imitation Policies via Flow-Matching World Modeling

    Jul 29, 2026Zhefeng Huang, Yilin Cai, Ankit Patel +3Robot Failure DetectionWorld Models

  13. StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation

    Jul 29, 2026Zijun Lin, Zeqing Wang, Cheston Tan +2Game World ModelsWorld Models

  14. Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control

    Jul 29, 2026Weili Zeng, Yitong Xing, Fulong Liu +10World ModelsEfficient VLA Inference

  15. CG-World: A Large-Scale World-State Dataset and Protocol for World Models

    Jul 29, 2026Yiming Cai, Fangjie Yu, Meiqing Yu +3World Model LearningWorld Models

  16. Learning Implicit Causal World Models from Multi-Agent Demonstrations

    Jul 28, 2026Jasorsi GhoshCausal Representation LearningCausal World Models

  17. Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance

    Jul 28, 2026Gaspard Lambrechts, Adrien Bolland, Daniel Ebi +1Reinforcement LearningWorld Models

  18. VisualPatchWorld: Code World Models as Latent Structured Representations for Planning

    Jul 28, 2026Jiaxin Bai, Jiaxuan XiongModel-Based PlanningWorld Models

  19. FeelWorld: Visuo-Tactile World Model for Hierarchical Contact Prediction and Planning

    Jul 27, 2026Wenxuan Ma, Chaofan Zhang, Chao Xue +4Contact-Rich ManipulationWorld Models for Robotics

  20. Scaling GUI Agents with Visual State Transitions

    Jul 27, 2026Xiangyan Liu, Kaixin Li, Haonan Wang +6World ModelsGUI Agents

  21. HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving

    Jul 23, 2026Quanfu Yu, Xian Wu, Hao Xu +1World ModelsAutonomous Driving

  22. Koopman Dreamer: Spectrally Constrained Latent Dynamics for Stable World-Model Imagination

    Jul 22, 2026Jiaqi Li, Xinglong Zhang, Haibin Xie +3Koopman Operator LearningLatent Dynamics Modeling

  23. PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration

    Jul 18, 2026Han Wang, Zijun Wang, Shuoshuo Xue +4World Model LearningWorld Models

  24. DSWorld: A Data Science World Model for Efficient Autonomous Agents

    Jul 17, 2026Zherui Yang, Fan Liu, Hao LiuWorld Model LearningWorld Models

  25. Orbis 2: A Hierarchical World Model for Driving

    Jul 17, 2026Sudhanshu Mittal, Arian Mousakhan, Silvio Galesso +5World ModelsHierarchical World Models